Google Deepmind updates Veo 3.1 with reference image function for more dynamic videos
Google Deepmind has updated Veo 3.1 with new features for generating video from reference images. The update enables more dynamic and expressive videos, even with simple text prompts, according to Google. Users can now keep characters consistent across multiple scenes and seamlessly combine different elements like textures, objects, and backgrounds.
The update also adds native support for vertical videos in 9:16 format, optimized for YouTube Shorts and the YouTube Create app along with other mobile platforms. Veo 3.1 now offers upscaling to 1080p and 4K resolution for professional productions. This likely means even more AI-generated content flooding YouTube, especially in the Shorts format.
The updates are available now in the Gemini app, YouTube, Flow, Google Vids, and through the Gemini API and Vertex AI. All generated videos include the invisible SynthID watermark to identify AI-generated content. Users can check in the Gemini app whether a video was created with Google AI.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe nowRead on for the full picture.
Subscribe for hype-free coverage.
- Full access to every article on THE DECODER
- No ads
- Join the comments and community discussions
- A weekly AI news recap via mail
- 6x/year: "AI Radar" — deep dives on the AI topics that matter most
- Daily AI news, always up to date
- Our full ten-year archive
- Covered by a team with 10+ years in AI